Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 592 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2516. Min Act: -0.0000

Data Index: 343073 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2347. Min Act: -0.0000

Data Index: 292572 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2111. Min Act: -0.0000

Data Index: 896080 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2351. Min Act: -0.0000

Data Index: 132953 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2271. Min Act: -0.0001

Data Index: 311282 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2135. Min Act: -0.0000

Data Index: 923642 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2112. Min Act: -0.0000

Data Index: 41494 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1333464 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1218196 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1344406 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2047. Min Act: -0.0000

Data Index: 521566 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2080. Min Act: -0.0001

Data Index: 964133 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1971. Min Act: -0.0000

Data Index: 898500 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1992. Min Act: -0.0000

Data Index: 548576 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1987. Min Act: -0.0000

Data Index: 42432 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1946. Min Act: -0.0001

Data Index: 318191 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1949. Min Act: -0.0001

Data Index: 964138 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1857. Min Act: -0.0000

Data Index: 274196 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1879. Min Act: -0.0000

Data Index: 943160 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2059. Min Act: -0.0000

Data Index: 520686 (C4 (Web Text))

Max Activating Token Index: 200